FluxML/Zygote.jl

gradient of keyword argument?

Open

#446 创建于 2020年1月6日

在 GitHub 查看
 (10 评论) (0 反应) (0 负责人)Julia (1,568 star) (220 fork)batch import
discussionhelp wantedperformance

描述

Is there any ways to compute the backward gradient of a keyword argument? For example, the var function can pass a pre-computed mean value as a keyword argument, but right now it seems like we can't get the gradient of it. This will have an effect on something like Flux.normalise.

贡献者指南

技术栈
无
领域
machine learning
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
4
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
3-5 days
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
needs maintainer response
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
JuliaAD basics
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
25
研究方向
Review the discussion in issue #446 to understand the request for gradient of keyword arguments. Examine the Zygote.jl codebase, particularly the parts handling `var` and `normalise`, to see where keyword arguments are processed. Check for any existing PRs or issues that may touch upon this feature. Propose a plan to extend the gradient computation to support keyword arguments while maintaining backward compatibility.
gradient of keyword argument? · FluxML/Zygote.jl#446 | Good First Issue